@evolinkai/cli 0.14.0 → 0.15.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +25 -8
- package/package.json +2 -2
- package/skills/evolink-cli/SKILL.md +12 -8
- package/skills/evolink-cli/references/ad-rebuild.md +76 -0
- package/skills/evolink-cli/references/usage-and-budget.md +3 -3
- package/src/cli.mjs +38 -6
- package/src/help.mjs +16 -3
- package/src/media.mjs +63 -19
- package/src/platform/core/src/services/batch-generation.js +7 -7
- package/src/platform/core/src/services/gpt-image-tokens.js +18 -16
- package/src/platform/core/src/services/omni-tokens.js +30 -15
- package/src/platform/core/src/services/pricing-quote-client.js +86 -22
- package/src/platform/core/src/services/pricing-rules-client.js +15 -3
- package/src/platform/core/src/services/pricing-rules-estimate.js +109 -45
- package/src/platform/core/src/services/qwen-tts-tokens.js +189 -0
- package/src/platform/core/src/tool-guidance.js +4 -4
- package/src/platform/core/src/tools/estimate-cost.js +6 -5
- package/src/platform/core/src/tools/generate.js +27 -26
- package/src/platform/core/src/tools/get-pricing-rules.js +5 -2
- package/src/platform/core/src/version.js +1 -1
- package/src/platform/source.json +28 -26
- package/src/state.mjs +18 -4
- package/src/workflow.mjs +138 -0
package/README.md
CHANGED
|
@@ -122,15 +122,15 @@ evolink tasks batch --ids TASK_A,TASK_B --json
|
|
|
122
122
|
evolink generate image --model MODEL --input-file input.json --skip-estimate --json
|
|
123
123
|
```
|
|
124
124
|
|
|
125
|
-
For video/audio, choose the corresponding generation command and a model's documented input. `estimate` never submits a task. Quotes are current for at most 24 hours and never outlive the returned pricing approval. They bind to the login and exact input,
|
|
125
|
+
For video/audio, choose the corresponding generation command and a model's documented input. `estimate` never submits a task. Quotes are current for at most 24 hours and never outlive the returned pricing approval. They bind to the login and exact input. Before submitting, `generate` estimates again: the same input at the approved price or lower submits, also under later pricing rules; a higher price (`price_changed`), a changed input (`quote_input_changed`) or an expired quote (`quote_expired`) needs a new estimate and approval. For a partial estimate only the part it prices is compared. `--confirm` conveys the user's approval; the CLI cannot verify a conversation by itself.
|
|
126
126
|
|
|
127
|
-
Show the estimated cost and ask the user to confirm the task. The CLI does not turn that estimate into a spending cap. If the user explicitly specifies a budget, compare the estimate with it; pause if it exceeds that budget or cannot be fully estimated. The legacy `--max-cost-usd` option remains compatible for this estimate comparison and does not limit the final charge. `--media-seconds` is a pricing hint, never a model parameter. Actual-usage billing requires explaining the relevant uncertainty; a missing price is refused. GPT Image token models (`gpt-image-1.5`, `gpt-image-2`, `gpt-image-2.5-*`, `gpt-image-2.6-*`) return a `token_billed` reference price, what EvoLink reserves at submission for the exact input; the task settles at the tokens it actually uses, and a `--max-cost-usd` budget must cover 1.5 times the reference price. Gemini Omni Flash video models (`gemini-omni-flash-*`, `gemini-omni-1.1-flash-*`, `gemini-omni-1.2-flash-*`) get a reference price the same way; give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k and the estimate also gives the price at
|
|
127
|
+
Show the estimated cost and ask the user to confirm the task. The CLI does not turn that estimate into a spending cap. If the user explicitly specifies a budget, compare the estimate with it; pause if it exceeds that budget or cannot be fully estimated. The legacy `--max-cost-usd` option remains compatible for this estimate comparison and does not limit the final charge. `--media-seconds` is a pricing hint, never a model parameter. Actual-usage billing requires explaining the relevant uncertainty; a missing price is refused. GPT Image token models (`gpt-image-1.5`, `gpt-image-2`, `gpt-image-2.5-*`, `gpt-image-2.6-*`) return a `token_billed` reference price, what EvoLink reserves at submission for the exact input; the task settles at the tokens it actually uses, and a `--max-cost-usd` budget must cover 1.5 times the reference price. Gemini Omni Flash video models (`gemini-omni-flash-*`, `gemini-omni-1.1-flash-*`, `gemini-omni-1.2-flash-*`) get a reference price the same way; give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k, and the estimate also gives the price at each input resolution (`reference_usage.input_resolution_prices`). `qwen-audio-3.1-tts-flash` gets a reference price the same way, from the length and kinds of characters of its text.
|
|
128
128
|
|
|
129
129
|
A failed or blocked estimate is not a quote. Catalog starting prices must not replace a task quote. Fix the reported problem and quote again while retaining the user's cap; do not ask for generation approval or submit using an invented total. Quote errors report `submission_allowed: false` and preserve the supplied budget.
|
|
130
130
|
|
|
131
131
|
`--skip-estimate` is for a user who explicitly said not to estimate or confirm, for one task, a batch or the rest of a conversation. `generate --model MODEL --input-file FILE --skip-estimate` (or `--inputs-file`) submits without a quote: the price is not checked, the task is charged by actual usage, and the result says so (`estimate_skipped`, `estimate_skip_reason`). Invalid input and an explicit `--max-cost-usd` are still refused; the command saves a record with its own request ID, so `tasks resume --quote QUOTE_ID` recovers an uncertain submission. When an estimate fails and the user has not opted out, ask once whether to generate anyway; on yes use `--skip-estimate`.
|
|
132
132
|
|
|
133
|
-
`--inputs-file` takes a JSON array, or JSONL with one input object per line, of 1-50 inputs for one model. `estimate --inputs-file` returns each input's price, the total and one quote for the batch; `generate --quote QUOTE_ID --confirm` submits every input at once (up to 10 at a time) and returns each input's task ID or error without waiting (`--wait` is for one task). Collect the results with `tasks batch --ids`. If some inputs were not submitted or their outcome is unknown, `tasks resume --quote QUOTE_ID` finishes the batch with the same request ID within
|
|
133
|
+
`--inputs-file` takes a JSON array, or JSONL with one input object per line, of 1-50 inputs for one model. `estimate --inputs-file` returns each input's price, the total and one quote for the batch; `generate --quote QUOTE_ID --confirm` submits every input at once (up to 10 at a time) and returns each input's task ID or error without waiting (`--wait` is for one task). Collect the results with `tasks batch --ids`. If some inputs were not submitted or their outcome is unknown, `tasks resume --quote QUOTE_ID` finishes the batch with the same request ID within 23 hours of its first submission: accepted inputs return their original tasks without a new charge. Never resubmit those inputs with a new estimate or generate command. `tasks resume` follows the same rule as `generate`: after a price rise or the quote's expiry nothing is sent; check `tasks batch --ids` and `tasks list` for what went through, then estimate only the inputs that did not and submit them as a new batch after approval.
|
|
134
134
|
|
|
135
135
|
For the five Seedance 2.5 generation models, `draft: true` with omitted `quality` uses `480p` for both pricing and submission. Estimates expose `effective_input` and `defaults_applied`; show these applied defaults before approval. Draft-to-video conversion and other model IDs retain their own inputs. The new checks match the resolved model and endpoint, including when catalog documentation is borrowed through an alias.
|
|
136
136
|
|
|
@@ -212,6 +212,22 @@ Task pagination returns `page`, `page_size` and `next_page`. `since`/`until` fil
|
|
|
212
212
|
|
|
213
213
|
All-result downloads accept up to 50 results. `--template '{task_id}-{index}.{ext}'` also supports `{kind}`; templates must produce distinct portable filenames without directories. Local receipts record sizes and SHA-256 hashes. `--resume` verifies saved files and downloads the remainder with the same task/directory/template. Changed files and unrelated existing files are preserved. Partial delivery returns successful files and per-result errors, exits nonzero, and leaves generation marked completed. Recover downloads using the original task; never regenerate to fix delivery.
|
|
214
214
|
|
|
215
|
+
## Workflows
|
|
216
|
+
|
|
217
|
+
A workflow is a set of step-by-step rules that EvoLink sends to a logged-in assistant, for example `ad-rebuild`: rebuild a reference ad of up to 30 seconds with your own product and creator. The package holds only the commands and a short entry page in the skill (`references/ad-rebuild.md`); the rules arrive after login.
|
|
218
|
+
|
|
219
|
+
```bash
|
|
220
|
+
evolink workflow rules ad-rebuild --json # overview, a run_id and the section list (free)
|
|
221
|
+
evolink workflow rules ad-rebuild --section plan --run RUN_ID --json
|
|
222
|
+
evolink workflow estimate ad-rebuild --run RUN_ID --seconds 15 --keyframes 6 --quality 720p --json # one estimated total (free)
|
|
223
|
+
evolink video analyze FILE_URL --run RUN_ID --step reference_analysis --purpose breakdown --json # paid, by tokens
|
|
224
|
+
evolink video analysis ANALYSIS_ID --json # collect a read that was still running (free)
|
|
225
|
+
```
|
|
226
|
+
|
|
227
|
+
- `workflow estimate` returns one total for the whole run from the published prices. The assistant shows that total once and asks once; the total depends mostly on the video's length and resolution.
|
|
228
|
+
- `video analyze` reads an EvoLink file link or result link (MP4 or MOV, within the workflow's length limit). It is charged by tokens to the logged-in account and is part of the workflow's estimated total. Repeating exactly the same command within 24 hours returns the first result without a new charge; a failed read exits non-zero with the service's error code and next step, and a read that was cut off still prints what was read.
|
|
229
|
+
- `workflow_unavailable` means the service does not offer workflows for this login yet.
|
|
230
|
+
|
|
215
231
|
## Usage and spending limits
|
|
216
232
|
|
|
217
233
|
```sh
|
|
@@ -241,11 +257,11 @@ All machine-readable commands accept `--json`. Stdout contains one envelope with
|
|
|
241
257
|
|
|
242
258
|
Run installation and tests on the test cloud host, not the development Mac. In this package directory: `npm ci`, `npm test`, `npm run test:mutations`, and `npm pack`. Tests use loopback fixtures and never spend production credits. Real paid acceptance requires a separate quote and user approval.
|
|
243
259
|
|
|
244
|
-
Development
|
|
260
|
+
The repository is `Evolink-AI/evolink-cli`. Development started in `deeplearning-goethe/evolink-cli`, which moved here on 2026-11-14 and is now archived: its history and release tags were carried over, while its earlier pull requests and GitHub releases stay in the archived repository. Package and command names and the service identity did not change; the npm package's repository link points here from its next release.
|
|
245
261
|
|
|
246
262
|
## Platform and MCP paths
|
|
247
263
|
|
|
248
|
-
The CLI uses REST and
|
|
264
|
+
The CLI uses REST for everything except the workflow commands. `workflow rules`, `workflow estimate`, `video analyze` and `video analysis` send one `tools/call` request each to the hosted MCP server named by `--server`, because a workflow's rules and the prompts behind a video read are kept on that service and never ship with this package. Browser chat clients continue to use remote MCP. Both paths currently share Passport resource permissions and the internal `EvoLink MCP (OAuth)` account limit. The authorization resource remains `https://mcp.evolink.ai/mcp`; it is distinct from the REST API destination. The gateway MCP emergency switch still applies to both paths. Total and daily limits, model permissions and pause apply to both clients; logging out revokes only the current OAuth session. Separate keys are optional when a project needs independent limits. Backend parameterized media Quote and its OAuth route must be enabled for account estimates.
|
|
249
265
|
|
|
250
266
|
The CLI vendors the reviewed shared platform module from the MCP repository with a SHA-256 source/artifact manifest in `src/platform/source.json`. Refresh it on the test host using `scripts/sync-platform-client.mjs`; never edit generated files. The MCP SDK is a development dependency for compatibility fixtures only. No extra package or MCP plugin installation is needed by CLI users.
|
|
251
267
|
|
|
@@ -286,7 +302,8 @@ A failed task is not charged: the credits reserved at submission are returned au
|
|
|
286
302
|
The local `quote_id` stores input binding, pricing fingerprint, integer UC subtotal
|
|
287
303
|
and expiry; there is no backend `estimate_id`. The local quote shares the core's
|
|
288
304
|
24-hour approval window and never outlives the returned approval. Before first submission, the CLI reads the rules
|
|
289
|
-
again
|
|
305
|
+
again: the same input at the approved price or lower submits, also under a later policy; a higher price, a changed
|
|
306
|
+
input or usage, or an expired quote needs a new estimate and approval.
|
|
290
307
|
Neither backend Quote nor new OAuth quote access is required. Existing login,
|
|
291
308
|
shared MCP key, quota and permissions remain.
|
|
292
309
|
|
|
@@ -303,6 +320,6 @@ Supply required measured or expected billing usage with
|
|
|
303
320
|
`--pricing-parameters '{"input_seconds":5.77}'`. Default `--pricing-source pricing_rules`
|
|
304
321
|
and old `account`/`public_reference` aliases use the same published full rules.
|
|
305
322
|
Partial estimates name missing usage and cannot check a budget. GPT Image token
|
|
306
|
-
models
|
|
307
|
-
token counts are not used for them. Estimates exclude personal discounts and do not reserve quota or guarantee
|
|
323
|
+
models, Gemini Omni Flash video models and `qwen-audio-3.1-tts-flash` need no token
|
|
324
|
+
counts; `--pricing-parameters` token counts are not used for them. Estimates exclude personal discounts and do not reserve quota or guarantee
|
|
308
325
|
the final charge.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@evolinkai/cli",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.15.0",
|
|
4
4
|
"description": "Generate images, video and audio with EvoLink, with browser login and quoted submissions.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -19,7 +19,7 @@
|
|
|
19
19
|
],
|
|
20
20
|
"repository": {
|
|
21
21
|
"type": "git",
|
|
22
|
-
"url": "git+https://github.com/
|
|
22
|
+
"url": "git+https://github.com/Evolink-AI/evolink-cli.git",
|
|
23
23
|
"directory": "packages/cli"
|
|
24
24
|
},
|
|
25
25
|
"publishConfig": {
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: evolink-cli
|
|
3
|
-
description: Generate or edit images, video, music and speech with the EvoLink CLI; discover models, quote tasks, upload references and deliver results. Applies when a terminal is available. Respect an explicitly requested different provider; exclude media analysis and repository development.
|
|
3
|
+
description: Generate or edit images, video, music and speech with the EvoLink CLI; discover models, quote tasks, upload references and deliver results. Also rebuild a reference ad with the user's own product and creator (the ad rebuild workflow). Applies when a terminal is available. Respect an explicitly requested different provider; exclude media analysis and repository development.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
<!-- evolink-media-cli-owned -->
|
|
@@ -55,6 +55,10 @@ If the assistant host denies a tool call, stop and explain the required permissi
|
|
|
55
55
|
|
|
56
56
|
Never ask for credentials in chat, read other applications' tokens, or use API keys on the command line. Use the installed CLI's OS credential store. Missing secure storage requires fixing that storage; do not invent a plaintext-token fallback.
|
|
57
57
|
|
|
58
|
+
## Workflows
|
|
59
|
+
|
|
60
|
+
When the user asks to rebuild, remake or clone a reference ad with their own product and creator, read [Ad rebuild workflow](references/ad-rebuild.md) first and follow it. Its step-by-step rules come from EvoLink after login: fetch them with `evolink workflow rules ad-rebuild --json`, section by section, and do not improvise the steps. It asks the user to confirm one estimated total (`evolink workflow estimate`) instead of each quote; that confirmation covers the quotes inside the total. `evolink video analyze` is paid and belongs to a workflow step; do not use it for other media analysis.
|
|
61
|
+
|
|
58
62
|
## Prepare and quote
|
|
59
63
|
|
|
60
64
|
For image edits, reference-based video, speech or music, read [media workflows](references/media-workflows.md) when selecting inputs. Model discovery and `models show` determine actual support; never invent input fields or infer model quality from search order.
|
|
@@ -63,7 +67,7 @@ For image edits, reference-based video, speech or music, read [media workflows](
|
|
|
63
67
|
- When comparing reference support, retrieving schemas or searching model documentation, read [Discovery and delivery extensions](references/capabilities.md). Use `models recommend`, `models schema` and `docs search` only when the installed CLI supports them. Keep the user's chosen model; recommendations explain alternatives, not automatic approval.
|
|
64
68
|
- For a local reference, run `evolink upload /absolute/path --json` and use its `file_url` in the model input. A chat attachment must have a readable local file or public URL. Keep the original `upload_id` if a response is lost. `uploads get ID` reads the saved receipt and, when supported by the file service, recovers a completed upload without resending bytes. If it returns `outcome_unknown` and `result_verified: false`, no result was verified; check the user's files before uploading again. A missing receipt from an older service does not prove the file failed to arrive. Legacy MCP upload slots require the older CLI version.
|
|
65
69
|
- Prepare a JSON input file using the model's documented parameters. Run `evolink estimate --model MODEL --input-file /absolute/input.json --json`, adding `--max-cost-usd` only for a user-specified cap. `--media-seconds` is an estimation hint, not a model `duration` parameter or a billing guarantee.
|
|
66
|
-
- Show the user the model, input/reference, number/duration, output settings, estimated total and material uncertainties. For a `token_billed` reference price (GPT Image token models
|
|
70
|
+
- Show the user the model, input/reference, number/duration, output settings, estimated total and material uncertainties. For a `token_billed` reference price (GPT Image token models, Gemini Omni Flash video models and `qwen-audio-3.1-tts-flash`), present it as a reference price: billed by actual token usage and settled when the task finishes, so the final charge may be lower or slightly higher. For a Gemini Omni video with an input or reference video, pass its length as `--media-seconds`; the reference counts that video at the highest resolution (4k), so also show the price the estimate gives at each input resolution. For other token billing or unknown duration, show the rates and state that the total is unknown. A partial estimate is not a total. Do not add a separate cap to the default confirmation; if the user gave a budget, say whether the estimate fits it.
|
|
67
71
|
|
|
68
72
|
Only a successful `estimate` response with `ok: true` and a returned `quote_id` can be approved. For invalid input, unavailable pricing, insufficient balance or an uncheckable cap, report the error and correct that problem before quoting again with the same budget. Do not invent a total or quote ID, run `generate --confirm`, or disable host permission controls.
|
|
69
73
|
|
|
@@ -75,17 +79,17 @@ Every paid task requires an explicit user approval of the quoted task, unless th
|
|
|
75
79
|
|
|
76
80
|
`evolink generate image|video|audio --quote QUOTE_ID --confirm --json`
|
|
77
81
|
|
|
78
|
-
The saved model and input are the submitted model and input. A
|
|
82
|
+
The saved model and input are the submitted model and input. A quote holds for its exact input until it expires (24 hours from the estimate) at the approved price or lower: `generate` estimates again before submitting and refuses a higher price (`price_changed`), a changed input (`quote_input_changed`) or an expired quote (`quote_expired`); then estimate again (free) and ask the user to approve the new quote. Do not remove or increase a user cap to make a request succeed. `--confirm` conveys an approval already obtained; it is not permission to approve on the user's behalf.
|
|
79
83
|
|
|
80
84
|
## Several images or tasks
|
|
81
85
|
|
|
82
86
|
For several images or tasks of one model, write the inputs (1–50, each like a single input) to a JSON array or JSONL file and run `evolink estimate --model MODEL --inputs-file /absolute/inputs.json --json`: one quote shows each input's price and the total, and one approval covers that batch. After approval, `evolink generate image|video|audio --quote QUOTE_ID --confirm --json` submits every input at once and returns each input's task ID or error right away (`--wait` does not apply to a batch). Collect the results with `evolink tasks batch --ids ID,ID --json` (free, up to 50 IDs). Tell the user the tasks generate at the same time. For tasks of different models, quote and submit each one separately. Do not rely on `n` for the count: some models, such as GPT Image, often return fewer images than `n`.
|
|
83
87
|
|
|
84
|
-
If some inputs were not submitted or their outcome is unknown, finish the batch with `evolink tasks resume --quote QUOTE_ID --json` within
|
|
88
|
+
If some inputs were not submitted or their outcome is unknown, finish the batch with `evolink tasks resume --quote QUOTE_ID --json` within 23 hours of its first submission: accepted inputs return their original tasks without a new charge, and only the rest are submitted. `tasks resume` sends nothing after a price rise or the quote's expiry: then check `evolink tasks batch --ids` and `evolink tasks list --since 2d` for what went through, estimate only the inputs that did not, and submit them as a new batch after the user approves. Never resubmit accepted, not-submitted or unknown-outcome inputs with a new estimate or generate command: that creates and charges new tasks. An input refused because it differs from what its request ID submitted earlier is a new task that needs a new estimate and approval.
|
|
85
89
|
|
|
86
90
|
## Recover and deliver
|
|
87
91
|
|
|
88
|
-
- Preserve `quote_id`, `client_request_id` and `task_id`. If submission outcome is unknown, use `tasks resume --quote QUOTE_ID` or `tasks list --since 30m --json`. Do not create a new quote/request ID to retry an uncertain submission. `tasks resume` replays the original request ID only within 23 hours of the first submission; after that (`recovery_window_passed`) check recent tasks instead. A known refused request can be corrected and quoted again.
|
|
92
|
+
- Preserve `quote_id`, `client_request_id` and `task_id`. If submission outcome is unknown, use `tasks resume --quote QUOTE_ID` or `tasks list --since 30m --json`. Do not create a new quote/request ID to retry an uncertain submission. `tasks resume` replays the original request ID only within 23 hours of the first submission; after that (`recovery_window_passed`) check recent tasks instead. It also sends nothing after a price rise (`price_changed`) or the quote's expiry (`quote_expired`): check `tasks list --since 2d` first, and only if the task did not go through, estimate again and ask for approval. A known refused request can be corrected and quoted again.
|
|
89
93
|
- `tasks list --status` accepts only the case-sensitive filters `processing`, `completed`, `failed`, `cancelled`. `processing` includes queued tasks. Do not use `pending`, `queued`, `canceled` or `all` as filter values. A task response may report `pending`; do not copy that response value into `--status`. Omit `--status` to read recent tasks across states, especially when recovering an uncertain submission that may already have completed or failed.
|
|
90
94
|
- For active tasks, use `evolink tasks list --status processing --json`. To find recent completed videos, use `evolink tasks list --status completed --type video --limit 50 --json`. Task-list `--type` accepts only `image`, `video`, `audio`; omit it for all types. `--limit` is 1–50 (default 20); `--since` accepts ISO 8601, Unix seconds or a relative time such as `30m`, `2h`, `1d`. It filters the selected page, not the entire history. Use `--page` and follow `next_page`; `--model` and `--until` narrow results. `total` is before time filtering. An empty list does not prove no task was submitted; retain the original IDs and use recovery. `cancelled` is a read filter, not a CLI cancellation feature.
|
|
91
95
|
- Poll with `tasks get TASK_ID --json` or `tasks wait TASK_ID --json`. Never poll with `generate`. Ctrl-C and the `tasks wait --timeout` limit stop only local waiting; they do not cancel the paid task. A `wait_timeout` error reports `status_check`: `verified` gives the last read `last_status` and its `read_at`, not a live status; `unverified` means the latest status could not be read. Continue with the returned `recovery` command, never with a new generation.
|
|
@@ -105,14 +109,14 @@ For setup problems, run `evolink doctor --agent NAME --json` if the installed ve
|
|
|
105
109
|
|
|
106
110
|
|
|
107
111
|
Estimates use published full pricing rules and show public default prices, excluding
|
|
108
|
-
personal discounts. Local approvals are current for up to 24 hours; submission verifies fresh rules
|
|
112
|
+
personal discounts. Local approvals are current for up to 24 hours from the estimate; submission verifies fresh rules: the same input at the approved price or lower submits, while a higher price, a changed input or an expired approval needs a new estimate and approval.
|
|
109
113
|
Use `evolink estimate --refresh-quote ID` only for an unsubmitted approval; preserve
|
|
110
114
|
the input and explicit user budget and obtain approval again. The refreshed quote
|
|
111
115
|
replaces the old one and keeps its request ID: submit only the newest quote, which
|
|
112
116
|
`quote_superseded` names. Supply missing billing
|
|
113
117
|
usage with `--pricing-parameters JSON`; never invent unknown token counts or media
|
|
114
|
-
lengths. GPT Image token models
|
|
118
|
+
lengths. GPT Image token models, Gemini Omni Flash video models (`gemini-omni-flash-*`, `gemini-omni-1.1-flash-*`, `gemini-omni-1.2-flash-*`) and `qwen-audio-3.1-tts-flash` need no
|
|
115
119
|
token counts: their reference price comes from the input, and a `--max-cost-usd` budget must cover 1.5 times it.
|
|
116
|
-
For a Gemini Omni video, give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k and the estimate also gives the price at
|
|
120
|
+
For a Gemini Omni video, give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k, and the estimate also gives the price at each input resolution. Partial subtotals cannot check a budget. If rules are unavailable or change,
|
|
117
121
|
pause and preserve the budget. Actual usage can change the final charge; final
|
|
118
122
|
settlement caps require gateway/Worker support.
|
|
@@ -0,0 +1,76 @@
|
|
|
1
|
+
# Ad rebuild workflow
|
|
2
|
+
|
|
3
|
+
Rebuild a reference ad as a new ad with the user's own product and creator. The structure, hook and rhythm stay; the person, product, room, words and music are new. The result is one finished vertical video with sound, generated in a single video task and delivered with a keyframe contact sheet, a verdict for every shot and the total cost.
|
|
4
|
+
|
|
5
|
+
This page is only the entry point. EvoLink sends the working rules for each step after login. Fetch them with `evolink workflow rules ad-rebuild --json` and follow them; do not improvise the steps from this page.
|
|
6
|
+
|
|
7
|
+
## What you need from the user
|
|
8
|
+
|
|
9
|
+
- The reference ad: a video of 30 seconds or less. If it is longer, ask for a segment of 30 seconds or less.
|
|
10
|
+
- Product images, one line on what the product does, and which claims are verified.
|
|
11
|
+
- A creator photo if a specific person should appear. Without one, a fictional adult creator is prepared when the ad needs a person.
|
|
12
|
+
- Choices that cannot be inferred: language, on-camera speech or voiceover, music, aspect ratio, length (up to 30 seconds) and resolution.
|
|
13
|
+
|
|
14
|
+
The user must own the product and creator material or have the rights to use it.
|
|
15
|
+
|
|
16
|
+
## Before you start
|
|
17
|
+
|
|
18
|
+
- The CLI must be logged in: `evolink balance --json` succeeds. If it reports `login_required`, ask the user to run `evolink auth login`, then stop until it is done.
|
|
19
|
+
- If `evolink workflow rules ad-rebuild --json` reports `workflow_unavailable`, the workflow is not offered for this login yet. Say so and stop.
|
|
20
|
+
- Never ask for an API key. Charges go to the logged-in account.
|
|
21
|
+
- Frames, crops and contact sheets: use local ffmpeg and ffprobe. If they are missing, ask before installing them.
|
|
22
|
+
|
|
23
|
+
## Commands
|
|
24
|
+
|
|
25
|
+
The rules name EvoLink tools. With the CLI, run these commands instead:
|
|
26
|
+
|
|
27
|
+
| The rules say | Run |
|
|
28
|
+
|---|---|
|
|
29
|
+
| `get_media_workflow` | `evolink workflow rules ad-rebuild [--section ID] --run RUN_ID --json` (leave `--run` out only on the first call) |
|
|
30
|
+
| `get_media_workflow` with `estimate` | `evolink workflow estimate ad-rebuild --run RUN_ID --seconds N --keyframes N [--quality 720p] [--aspect-ratio 9:16] [--creator-images N] --json` |
|
|
31
|
+
| `analyze_video` | `evolink video analyze FILE_URL --run RUN_ID --step STEP --purpose breakdown\|sound\|compare [--target-file FILE] [--attempt N] --json` |
|
|
32
|
+
| `get_video_analysis` | `evolink video analysis ANALYSIS_ID --json` |
|
|
33
|
+
| `upload_file`, `prepare_upload` | `evolink upload /absolute/path --json` |
|
|
34
|
+
| `search_models`, `get_model` | `evolink models search --query TEXT --json`, `evolink models show MODEL --json` |
|
|
35
|
+
| `estimate_cost` | `evolink estimate --model MODEL --input-file FILE --json` |
|
|
36
|
+
| `generate_image`, `generate_video`, `generate_audio` | `evolink generate image\|video\|audio --quote ID --confirm --json` |
|
|
37
|
+
| `get_task`, `list_tasks` | `evolink tasks get\|wait\|list\|batch ... --json` |
|
|
38
|
+
| `check_balance` | `evolink balance --json` |
|
|
39
|
+
| `make_frames` | not in the CLI: use local ffmpeg |
|
|
40
|
+
|
|
41
|
+
The first `workflow rules` answer returns a `run_id` and the list of sections. Pass that `run_id` with `--run` on every later `workflow` and `video` command of the same rebuild, and fetch each section when you reach its step.
|
|
42
|
+
|
|
43
|
+
For a comparison (`--purpose compare`), write the whole-ad target sheet and timeline to a text file and pass it with `--target-file`.
|
|
44
|
+
|
|
45
|
+
## Steps
|
|
46
|
+
|
|
47
|
+
0. Check inputs and confirm the cost
|
|
48
|
+
1. Read the reference
|
|
49
|
+
2. Write the target
|
|
50
|
+
3. Plan the whole ad
|
|
51
|
+
4. Build and check all keyframes
|
|
52
|
+
5. Build the complete video input
|
|
53
|
+
6. Generate and check
|
|
54
|
+
7. Deliver
|
|
55
|
+
|
|
56
|
+
## Cost: one estimate, one confirmation
|
|
57
|
+
|
|
58
|
+
- Before the user confirms, do only free work: login and balance, the reference's duration and aspect ratio, frames and shot count, rules and prices. `workflow rules` and `workflow estimate` are free. `video analyze` is paid.
|
|
59
|
+
- Present the one estimated total from `workflow estimate` and what it covers, and ask once. The total depends mostly on the length and resolution of the video. Charges are then made step by step as the work runs.
|
|
60
|
+
- That confirmation is the approval for the quotes inside the total: after it, estimate each generation and submit it with `--confirm` without asking again, as long as the running total stays within the estimate.
|
|
61
|
+
- Ask again only when the total would be exceeded, when a decision is the user's, or when the finished ad needs a new attempt.
|
|
62
|
+
- If the user asks what the total includes, say the total and what it covers. Every call is listed in the dashboard history: https://evolink.ai/dashboard
|
|
63
|
+
|
|
64
|
+
## If something stops the run
|
|
65
|
+
|
|
66
|
+
- **Balance too low.** Nothing is charged for the refused step. Give the top-up link from the error. After the user tops up, continue from the same step; finished steps are reused.
|
|
67
|
+
- **A generation fails.** It is not charged. Retry at most twice for a temporary failure, then stop and explain.
|
|
68
|
+
- **A video read fails.** Follow the next step in the error. Repeat exactly the same command when it says so: a finished read is returned without a new charge. Add `--attempt 2` only when the error says to raise the attempt.
|
|
69
|
+
- **The terminal or the conversation restarts.** Fetch the rules again with the same `--run`, and look for submitted tasks with `evolink tasks list --json` before submitting anything again. Result links stay downloadable for 24 hours and uploads for 72 hours.
|
|
70
|
+
|
|
71
|
+
## Rights and limits
|
|
72
|
+
|
|
73
|
+
- The reference guides structure only. The new ad must not show the reference's people, faces, clothing, room, brand or audio.
|
|
74
|
+
- Do not invent logos, prices, statistics or product claims. Use only claims the user confirmed.
|
|
75
|
+
- Some image and video models refuse inputs that look like real people. Report a refusal; never reword a prompt to get past review.
|
|
76
|
+
- One creator and one product per run unless the user asks otherwise.
|
|
@@ -18,15 +18,15 @@ A final task/workflow cap requires server-side reservation and settlement enforc
|
|
|
18
18
|
|
|
19
19
|
|
|
20
20
|
Estimates use published full pricing rules and show public default prices, excluding
|
|
21
|
-
personal discounts. Local approvals are current for up to 24 hours; submission verifies fresh rules
|
|
21
|
+
personal discounts. Local approvals are current for up to 24 hours from the estimate; submission verifies fresh rules: the same input at the approved price or lower submits, while a higher price, a changed input or an expired approval needs a new estimate and approval.
|
|
22
22
|
Use `evolink estimate --refresh-quote ID` only for an unsubmitted approval; preserve
|
|
23
23
|
the input and explicit user budget and obtain approval again. The refreshed quote
|
|
24
24
|
replaces the old one and keeps its request ID: submit only the newest quote, which
|
|
25
25
|
`quote_superseded` names. Supply missing billing
|
|
26
26
|
usage with `--pricing-parameters JSON`; never invent unknown token counts or media
|
|
27
|
-
lengths. GPT Image token models
|
|
27
|
+
lengths. GPT Image token models, Gemini Omni Flash video models (`gemini-omni-flash-*`, `gemini-omni-1.1-flash-*`, `gemini-omni-1.2-flash-*`) and `qwen-audio-3.1-tts-flash` need no
|
|
28
28
|
token counts: their reference price comes from the input, and a `--max-cost-usd` budget must cover 1.5 times it.
|
|
29
|
-
For a Gemini Omni video, give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k and the estimate also gives the price at
|
|
29
|
+
For a Gemini Omni video, give an input or reference video's length with `--media-seconds` (for several reference videos, the longest one's). EvoLink reads that video's resolution at submission, so the reference counts it at 4k, and the estimate also gives the price at each input resolution. Partial subtotals cannot check a budget. If rules are unavailable or change,
|
|
30
30
|
pause and preserve the budget. Actual usage can change the final charge; final
|
|
31
31
|
settlement caps require gateway/Worker support.
|
|
32
32
|
|
package/src/cli.mjs
CHANGED
|
@@ -9,6 +9,7 @@ import { upload, download, downloadAll, getUpload } from './files.mjs';
|
|
|
9
9
|
import { commandHelp } from './help.mjs';
|
|
10
10
|
import { installSkill, skillStatus, validateAgent } from './skills.mjs';
|
|
11
11
|
import { doctor } from './doctor.mjs';
|
|
12
|
+
import { Workflows } from './workflow.mjs';
|
|
12
13
|
import { setup } from './setup.mjs';
|
|
13
14
|
import { checkForUpdate, updateNotice } from './update.mjs';
|
|
14
15
|
import { CLI_VERSION } from './version.mjs';
|
|
@@ -82,6 +83,15 @@ const HELP = `EvoLink CLI ${CLI_VERSION} (Node.js 22+)
|
|
|
82
83
|
uploads get ID Read a saved upload receipt (free)
|
|
83
84
|
download TASK_ID --output FILE [--index N]
|
|
84
85
|
download TASK_ID --all --output-dir DIR [--template NAME] [--resume]
|
|
86
|
+
workflow rules NAME [--section ID] [--run RUN_ID]
|
|
87
|
+
Step-by-step rules of an EvoLink workflow (free)
|
|
88
|
+
workflow estimate NAME --seconds N --keyframes N [--run RUN_ID]
|
|
89
|
+
[--quality 480p|720p|1080p] [--aspect-ratio RATIO] [--creator-images N]
|
|
90
|
+
One estimated total for a whole run (free)
|
|
91
|
+
video analyze FILE_URL --run RUN_ID --step STEP --purpose PURPOSE
|
|
92
|
+
[--target-file FILE] [--attempt N]
|
|
93
|
+
Read a video for a workflow step (paid, by tokens)
|
|
94
|
+
video analysis ANALYSIS_ID Collect a read that was still running (free)
|
|
85
95
|
skills install [--agent NAME] [--replace-modified]
|
|
86
96
|
Install or update; back up replaced files
|
|
87
97
|
skills status [--agent NAME] Check installed skill content and CLI version
|
|
@@ -109,12 +119,15 @@ newer release exists. EVOLINK_CLI_UPDATE_CHECK=0 turns these npm registry checks
|
|
|
109
119
|
Login timeout: 30-900 seconds, default 180. On SSH, forward the callback port.
|
|
110
120
|
The CLI verifies skill files; your assistant must confirm it loads evolink-cli.
|
|
111
121
|
Quotes are current for at most 24 hours, never beyond the returned approval expiry.
|
|
112
|
-
generate estimates again before submitting:
|
|
113
|
-
|
|
122
|
+
generate estimates again before submitting: the same input at the approved price or
|
|
123
|
+
lower submits; a higher price, a changed input or an expired quote needs a new approval.
|
|
114
124
|
--confirm is only for an already approved quote. --skip-estimate is only for a user
|
|
115
125
|
who explicitly said not to estimate or confirm.
|
|
116
126
|
A batch quote submits all its inputs in one call; tasks resume finishes the rest
|
|
117
|
-
with the same request ID within
|
|
127
|
+
with the same request ID within 23 hours, while the quote holds.
|
|
128
|
+
Workflows (for example ad-rebuild) need the login: their rules and video reads come
|
|
129
|
+
from the EvoLink MCP service named by --server. video analyze is charged to the account;
|
|
130
|
+
the same command repeated within 24 hours returns the first result without a new charge.
|
|
118
131
|
Spending caps protect the estimate at submission, not final settlement.
|
|
119
132
|
Ctrl-C stops local waiting; submitted tasks continue on EvoLink.
|
|
120
133
|
`;
|
|
@@ -123,7 +136,8 @@ Ctrl-C stops local waiting; submitted tasks continue on EvoLink.
|
|
|
123
136
|
const NO_UPDATE_NOTICE = new Set(['setup', 'doctor', 'auth login', 'auth status']);
|
|
124
137
|
|
|
125
138
|
const OPTIONS = Object.fromEntries(['server', 'api-url', 'files-url', 'query', 'type', 'limit', 'model', 'modality', 'view', 'product-id', 'operation', 'lifecycle', 'input', 'input-file', 'inputs-file', 'prompt', 'media-seconds',
|
|
126
|
-
'pricing-source', 'pricing-parameters', 'refresh-quote', 'max-cost-usd', 'quote', 'timeout', 'status', 'since', 'until', 'page', 'ids', 'references', 'max-pages', 'output', 'output-dir', 'template', 'index', 'upload-path', 'agent'
|
|
139
|
+
'pricing-source', 'pricing-parameters', 'refresh-quote', 'max-cost-usd', 'quote', 'timeout', 'status', 'since', 'until', 'page', 'ids', 'references', 'max-pages', 'output', 'output-dir', 'template', 'index', 'upload-path', 'agent',
|
|
140
|
+
'section', 'run', 'seconds', 'keyframes', 'quality', 'aspect-ratio', 'creator-images', 'step', 'purpose', 'target-file', 'attempt'].map(k => [k, { type: 'string' }]));
|
|
127
141
|
for (const k of ['json', 'token-stdin', 'no-browser', 'replace-modified', 'confirm', 'skip-estimate', 'wait', 'all', 'resume', 'help', 'version']) OPTIONS[k] = { type: 'boolean' };
|
|
128
142
|
|
|
129
143
|
function number(value, name, min, max, integer = false) {
|
|
@@ -148,6 +162,8 @@ export function validateCommand(args, options) {
|
|
|
148
162
|
'tasks get': [3], 'tasks wait': [3, 'timeout'], 'tasks batch': [2, 'ids'], 'tasks list': [2, 'type', 'status', 'since', 'until', 'model', 'page', 'limit'], 'tasks resume': [2, 'quote'],
|
|
149
163
|
upload: [2, 'upload-path'], 'uploads get': [3], download: [2, 'output', 'index', 'all', 'output-dir', 'template', 'resume'],
|
|
150
164
|
'skills install': [2, 'agent', 'replace-modified'], 'skills status': [2, 'agent'], doctor: [1, 'agent'],
|
|
165
|
+
'workflow rules': [3, 'section', 'run'], 'workflow estimate': [3, 'run', 'seconds', 'keyframes', 'quality', 'aspect-ratio', 'creator-images'],
|
|
166
|
+
'video analyze': [3, 'run', 'step', 'purpose', 'target-file', 'attempt'], 'video analysis': [3],
|
|
151
167
|
};
|
|
152
168
|
const route = routes[`${command} ${action}`] || routes[command];
|
|
153
169
|
requireThat(route && args.length === route[0], 'unknown_command', 'Unknown command or argument count. Run evolink --help.');
|
|
@@ -255,7 +271,7 @@ async function estimateArgs(options) {
|
|
|
255
271
|
return { model: options.model, ...body, ...(pricingParameters !== undefined ? { pricing_parameters: pricingParameters } : {}), ...(options['pricing-source'] ? { pricing_source: options['pricing-source'] } : {}), ...(media !== undefined ? { media_seconds: media } : {}), ...(cap !== undefined ? { max_cost_usd: cap } : {}) };
|
|
256
272
|
}
|
|
257
273
|
|
|
258
|
-
export async function dispatch(positionals, options, { state, server, credentials, client, mcp = client, signal, progress, skillHome, updates, budget }) {
|
|
274
|
+
export async function dispatch(positionals, options, { state, server, credentials, client, mcp = client, workflows, signal, progress, skillHome, updates, budget }) {
|
|
259
275
|
// login, setup and doctor always ask the registry and report the outcome, including a disabled check;
|
|
260
276
|
// loopback test resources never contact it.
|
|
261
277
|
const update = () => checkForUpdate({ state, server, force: true, signal, ...updates });
|
|
@@ -343,6 +359,21 @@ export async function dispatch(positionals, options, { state, server, credential
|
|
|
343
359
|
if (command === 'setup') return setup({ state, server, credentials, client, agent: options.agent, skillHome,
|
|
344
360
|
noBrowser: options['no-browser'], timeout: options.timeout === undefined ? undefined : Number(options.timeout) * 1000, signal, progress, update });
|
|
345
361
|
if (command === 'doctor') return doctor({ state, server, credentials, client, agent: options.agent, skillHome, update });
|
|
362
|
+
if ((command === 'workflow' || command === 'video') && workflows) {
|
|
363
|
+
if (command === 'workflow' && action === 'rules') return workflows.rules(id, { section: options.section, run: options.run });
|
|
364
|
+
if (command === 'workflow' && action === 'estimate') {
|
|
365
|
+
requireThat(options.seconds !== undefined && options.keyframes !== undefined, 'missing_option', 'Pass --seconds and --keyframes: the planned video length and the expected number of keyframe images.');
|
|
366
|
+
requireThat(options.quality === undefined || ['480p', '720p', '1080p'].includes(options.quality), 'invalid_option', 'quality must be 480p, 720p or 1080p.');
|
|
367
|
+
requireThat(options['aspect-ratio'] === undefined || ['16:9', '9:16', '1:1', '4:3', '3:4', '21:9'].includes(options['aspect-ratio']), 'invalid_option', 'aspect-ratio must be 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9.');
|
|
368
|
+
return workflows.estimate(id, { run: options.run, seconds: number(options.seconds, 'seconds', 1, 600, true), keyframes: number(options.keyframes, 'keyframes', 1, 100, true),
|
|
369
|
+
quality: options.quality, aspectRatio: options['aspect-ratio'], creatorImages: number(options['creator-images'], 'creator-images', 0, 10, true) });
|
|
370
|
+
}
|
|
371
|
+
if (command === 'video' && action === 'analyze') {
|
|
372
|
+
requireThat(options.run && options.step && options.purpose, 'missing_option', 'Pass --run, --step and --purpose, as the workflow rules name them.');
|
|
373
|
+
return workflows.analyze(id, { run: options.run, step: options.step, purpose: options.purpose, targetFile: options['target-file'], attempt: number(options.attempt, 'attempt', 1, 3, true) });
|
|
374
|
+
}
|
|
375
|
+
if (command === 'video' && action === 'analysis') return workflows.analysis(id);
|
|
376
|
+
}
|
|
346
377
|
throw new CliError('unknown_command', 'Unknown command or missing argument. Run evolink --help.');
|
|
347
378
|
}
|
|
348
379
|
|
|
@@ -410,7 +441,8 @@ export async function main(argv = process.argv.slice(2), io = { stdout: process.
|
|
|
410
441
|
const client = new Api(credentials, { signal: controller.signal, apiUrl: options['api-url'], filesUrl: options['files-url'] });
|
|
411
442
|
// Only a fully validated command checks: invalid tokens and service URLs fail without contacting npm.
|
|
412
443
|
if (!NO_UPDATE_NOTICE.has(positionals[0]) && !NO_UPDATE_NOTICE.has(positionals.slice(0, 2).join(' '))) checkUpdate(server);
|
|
413
|
-
const
|
|
444
|
+
const workflows = new Workflows(credentials, { signal: controller.signal });
|
|
445
|
+
const result = publicView(await dispatch(positionals, options, { state, server, credentials, client, workflows, signal: controller.signal, progress: message => io.stderr.write(message + '\n'), updates, budget }));
|
|
414
446
|
const view = { schema_version: 1, ...result, ok: result.ok !== false };
|
|
415
447
|
io.stdout.write(options.json ? JSON.stringify(view) + '\n' : `${result.text || JSON.stringify(view, null, 2)}\n${result.quote_id ? `Quote: ${result.quote_id}\n` : ''}`);
|
|
416
448
|
if (!view.ok) process.exitCode = view.error?.code === 'interrupted' ? 130 : 1;
|
package/src/help.mjs
CHANGED
|
@@ -18,13 +18,13 @@ const COMMANDS = {
|
|
|
18
18
|
'models search': ['[options]', 'Search currently available models; search order is not a quality ranking.', { query: string('Search keywords'), type: allMedia, limit: integer(1, 50, 20), page: integer(1, 100000, 1) }],
|
|
19
19
|
'models show': ['MODEL', 'Read documented parameters, example input, reference fields and pricing. Free.', {}],
|
|
20
20
|
'models pricing': ['[options]', 'Read public default pricing rules without login. Decimal-string rates, minimums, tiers and expressions are configuration references, not account prices, quotes, bills or final spending caps. Coverage follows returned policies and legacy text adapters; empty results do not mean free.', {
|
|
21
|
-
model: string('
|
|
21
|
+
model: string('Model ID or a published alias (case-insensitive); omit for the filtered list'), 'product-id': string('Product ID'), operation: string('Operation, e.g. text_generation'),
|
|
22
22
|
modality: choice(['text', 'image', 'video', 'audio']), lifecycle: choice(['active', 'preview', 'deprecated']), view: { ...choice(['summary', 'full']), default: 'full' },
|
|
23
23
|
}],
|
|
24
24
|
'models schema': ['MODEL', 'Read versioned input and generation-submission response schemas. The response schema may omit final task outputs; runtime constraints also apply.', {}],
|
|
25
25
|
'models recommend': ['--type TYPE [options]', 'Compare documented available alternatives with selection reasons. Unit rates are not total quotes.', { type: media, query: string('Search keywords; every term must match'), references: string('Comma-separated image,video,audio'), limit: integer(1, 10, 3) }],
|
|
26
26
|
'docs search': ['--query TEXT [options]', 'Search versioned official model reference excerpts, not the live full website.', { query: string('Required model reference keywords'), type: allMedia, limit: integer(1, 20, 5) }],
|
|
27
|
-
estimate: ['--model MODEL --input-file FILE|--inputs-file FILE [options] | --refresh-quote ID', 'Prepare an estimate valid until the returned approval expiry, at most 24 hours
|
|
27
|
+
estimate: ['--model MODEL --input-file FILE|--inputs-file FILE [options] | --refresh-quote ID', 'Prepare an estimate valid until the returned approval expiry, at most 24 hours from the estimate. generate estimates again before submitting: the same input at the approved price or lower submits; a higher price, a changed input or an expired quote needs a new estimate and approval. Show the estimated cost and material uncertainty, then obtain user approval. No spending cap is created from the estimate. --inputs-file prepares one quote for a batch: one approval covers all its inputs.', {
|
|
28
28
|
model: string('Required model ID'), input: string('JSON object; mutually exclusive with input-file and inputs-file'), 'input-file': string('Local JSON file; mutually exclusive with input and inputs-file'),
|
|
29
29
|
'inputs-file': string('Local JSON array or JSONL file of 1-50 inputs for one model, estimated and later submitted together'), prompt: string('Optional prompt; not with inputs-file'),
|
|
30
30
|
'pricing-source': choice(['account', 'public_reference']), 'pricing-parameters': string('JSON object containing declared billing usage'),
|
|
@@ -37,7 +37,7 @@ const COMMANDS = {
|
|
|
37
37
|
'tasks list': ['[options]', 'Page through account tasks. since/until filter only the selected page; total is before time filtering. Empty results do not prove no task was submitted.', {
|
|
38
38
|
status: choice(['processing', 'completed', 'failed', 'cancelled']), type: media, since: time, until: time, model: string('Exact model ID'), page: integer(1, 100000, 1), limit: integer(1, 50, 20),
|
|
39
39
|
}],
|
|
40
|
-
'tasks resume': ['--quote ID', 'Recover an uncertain submission, or finish a partly submitted batch, with the original request ID within
|
|
40
|
+
'tasks resume': ['--quote ID', 'Recover an uncertain submission, or finish a partly submitted batch, with the original request ID within 23 hours of its first submission. Accepted inputs return their tasks without a new charge. Its quote must still hold: after a price rise or its expiry nothing is sent; check tasks list for what went through and estimate only the rest as a new generation or batch. Use generate for an approved quote that has never been submitted.', { quote: string('Original quote ID') }],
|
|
41
41
|
usage: ['[options]', 'Summarize reported completed-task credits by creation time. Account-wide retained tasks; bounded scan with coverage and missing-cost metadata. Excludes payments/refunds and pending reservations. Not a bill or final budget.', {
|
|
42
42
|
since: { ...time, default: '30d' }, until: time, model: string('Exact model ID'), type: media, 'max-pages': integer(1, 20, 5),
|
|
43
43
|
}],
|
|
@@ -47,6 +47,19 @@ const COMMANDS = {
|
|
|
47
47
|
output: string('New file path, for a single result'), index: integer(1, 50, 1), all: flag, 'output-dir': string('Directory, required with all'),
|
|
48
48
|
template: { ...string('Filename placeholders: {task_id}, {index}, {kind}, {ext}; no directories'), default: '{task_id}-{index}.{ext}' }, resume: flag,
|
|
49
49
|
}],
|
|
50
|
+
'workflow rules': ['NAME [options]', 'Read the step-by-step rules of an EvoLink workflow (for example ad-rebuild) from the signed-in service. The first call returns the overview, a run_id and the section list; pass --run on every later call so the whole run uses one version of the rules. Free.', {
|
|
51
|
+
section: string('Section ID from an earlier answer; the overview when omitted'), run: string('run_id returned by the first call of this run'),
|
|
52
|
+
}],
|
|
53
|
+
'workflow estimate': ['NAME --seconds N --keyframes N [options]', 'One estimated total for a whole workflow run, from the published prices of its default models. Show the user this total and what it covers before any paid step. Nothing is charged.', {
|
|
54
|
+
run: string('run_id of this run'), seconds: integer(1, 600), keyframes: integer(1, 100), quality: choice(['480p', '720p', '1080p']),
|
|
55
|
+
'aspect-ratio': choice(['16:9', '9:16', '1:1', '4:3', '3:4', '21:9']), 'creator-images': integer(0, 10, 0),
|
|
56
|
+
}],
|
|
57
|
+
'video analyze': ['FILE_URL --run RUN_ID --step STEP --purpose PURPOSE [options]', 'Read a video for a workflow step. Paid, by tokens, to the signed-in account, and part of the workflow\'s estimated total: do not run it before the user confirmed that total. FILE_URL is an EvoLink file link (from evolink upload) or an EvoLink result link to an MP4 or MOV. The same command within 24 hours returns the first result without a new charge. A slow read returns an analysis_id for video analysis.', {
|
|
58
|
+
run: string('Required run_id from workflow rules'), step: string('Required step name from the workflow rules, e.g. reference_analysis'),
|
|
59
|
+
purpose: string('Required purpose named by the workflow rules, e.g. breakdown, sound, compare'),
|
|
60
|
+
'target-file': string('Local text file with the target to compare the video against; only for a comparison'), attempt: integer(1, 3, 1),
|
|
61
|
+
}],
|
|
62
|
+
'video analysis': ['ANALYSIS_ID', 'Collect the result of a video analyze call that was still running. Free.', {}],
|
|
50
63
|
'skills install': ['[options]', 'Install or synchronize bundled skill files; protect modified files and back up replacements.', { agent, 'replace-modified': flag }],
|
|
51
64
|
'skills status': ['[options]', 'Compare installed skill contents and package version.', { agent }],
|
|
52
65
|
doctor: ['[options]', 'Check prerequisites, connection, model discovery, skill contents and CLI updates separately. An available update, and installed skill findings without --agent, are guidance only. Free.', { agent }],
|